Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 68 for “"3D scene"”.

  1. CAD Model-Based 3D Scene Reconstruction

    Accurate scene reconstruction from an image or a video is essential for various applications in robotics and augmented reality. One common method involves retrieving the best-matching CAD model for each observed object from a database and aligning it with the corresponding input. This technique …

    cambridge Repository record for CAD Model-Based 3D Scene Reconstruction (opens in a new tab)

  2. Generative 3D scene modeling: algorithm and applications

    The ability to generate realistic and functional 3D scenes at scale is becoming increasingly important across domains such as agriculture, autonomous driving, immersive gaming, and robot learning. However, manually constructing such environments is prohibitively expensive and often introduces …

    uiuc Repository record for Generative 3D scene modeling: algorithm and applications (opens in a new tab)

  3. Towards controllable and consistent 3D scene editing

    Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01

    uiuc Repository record for Towards controllable and consistent 3D scene editing (opens in a new tab)

  4. Articulated 3D Scene Graphs from Egocentric Vision

    … typically approach building metric-semantic scene representations from the robot’s own sensors and cameras. However, these “first person” maps inherit the robot’s own limitations due to its embodiment or skillset, which may leave many aspects of the environment unexplored. For example, the …

    mit Repository record for Articulated 3D Scene Graphs from Egocentric Vision (opens in a new tab)

  5. Scaling 3D Scene Perception via Probabilistic Programming

    Understanding and interpreting the 3D structure of the world is a central challenge in artificial intelligence. Our physical world is 3D, yet our AI systems often “see” that world through pixels and images. In order to build truly intelligent AI systems, we must go beyond pixels and images and …

    mit Repository record for Scaling 3D Scene Perception via Probabilistic Programming (opens in a new tab)

  6. Underwater Refractive Camera Calibration and 3D Scene Reconstruction

    … focuses on refractive camera calibration and 3D reconstruction. It starts with investigating geometric models and calibration methods for dome-port camera systems, then introduces an open-source refractive Structure-from-Motion (SfM) solution that integrates refraction throughout the …

    cau-kiel Repository record for Underwater Refractive Camera Calibration and 3D Scene Reconstruction (opens in a new tab)

  7. Enhancing 3D Scene Graph Generation with Multimodal Embeddings

    3D Scene Graphs are expressive map representations for scene understanding in robotics and computer vision. Current approaches for automated zero-shot 3D Scene Graph generation rely on spatial ontologies that relate objects with the semantic locations they are found in (e.g., a fork is found in a …

    mit Repository record for Enhancing 3D Scene Graph Generation with Multimodal Embeddings (opens in a new tab)

  8. The robot's vista space : a computational 3D scene analysis

    … structures they are talking about, and what scene elements they are going to manipulate. This thesis focuses on the analysis of a robot's vista space. Mechanisms for extracting relevant spatial information are developed which enable the robot to recognize in which place it is, to detect the …

    bielefeld Repository record for The robot's vista space : a computational 3D scene analysis (opens in a new tab)

  9. LARGE-SCALE NEURAL 3D SCENE RECONSTRUCTION, RENDERING, AND BEYOND

    This thesis advances neural 3D reconstruction into a scalable and robust process for real-world applications. While techniques like NeRF and 3D Gaussian Splatting (3DGS) show promise, they face challenges in scalability, robustness to imperfect camera poses, and consistency across distributed …

    nus Repository record for LARGE-SCALE NEURAL 3D SCENE RECONSTRUCTION, RENDERING, AND BEYOND (opens in a new tab)

  10. 3D scene and object parsing from a single image

    The term 3D parsing refers to the process of segmenting and labeling the 3D space into expressive categories of voxels, point clouds or surfaces. Humans can effortlessly perceive the 3D scene and the unseen part of an object from a single image with a limited field of view. In the same sense, a …

    uiuc Repository record for 3D scene and object parsing from a single image (opens in a new tab)

  11. Towards Reinforcement-Learning-based Robot Navigation with 3D Scene Graphs

    … of RL models guiding autonomous agents, we use 3D Scene Graphs (3DSGs) as a map representation. Previous work has shown that RL policies based on offline 3DSGs produce promising results in simulation, and this work takes initial steps towards extending these findings to 3DSGs produced online by …

    mit Repository record for Towards Reinforcement-Learning-based Robot Navigation with 3D Scene Graphs (opens in a new tab)

  12. Towards Self-Supervised Object Representations and 3D Scene Graph Based Navigation

    3D Scene Graphs are powerful hierarchical representations of environments that combine spatial and semantic information into multiple levels of abstraction. 3D Scene Graphs are useful for a wide range of planning tasks in robotics that benefit from high-level semantic knowledge, and also capture …

    mit Repository record for Towards Self-Supervised Object Representations and 3D Scene Graph Based Navigation (opens in a new tab)

  13. Build realistic and interactive 3D scene simulation from in-the-wild videos

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01

    uiuc Repository record for Build realistic and interactive 3D scene simulation from in-the-wild videos (opens in a new tab)

  14. Alive Scene: Participatory Multimodal AI Framework for Collective Narratives in Dynamic 3D Scene

    This thesis introduces "Alive Scene," an online participatory platform for recording dynamic 3D environments and building collective interpretations of objects, events, and atmospheres within them. For instance, a user can browse a recording of a room and describe objects or events to locate them; …

    mit Repository record for Alive Scene: Participatory Multimodal AI Framework for Collective Narratives in Dynamic 3D Scene (opens in a new tab)

  15. Hydra: A Spatial Perception Engine for Constructing and Optimizing 3D Scene Graphs in Real-time

    3D scene graphs have emerged as a powerful map representation for robotics. Scene graphs encode spatial and semantic concepts at multiple levels of abstraction as nodes in a graph, and use edges to represent relationships. Such representations offer an efficient way to model diverse environments, …

    mit Repository record for Hydra: A Spatial Perception Engine for Constructing and Optimizing 3D Scene Graphs in Real-time (opens in a new tab)

  16. Dynamic Scene Editing via Semantically Trained 3D Guassians

    Image-based 3D scene reconstruction continues to be a challenge as it involves solving both the sufficient 3D representation problem and the 3D reconstruction itself. One approach to tackle the rendering problem is 3D Gaussian Splatting because of its potential to produce fast and realistic renders …

    mit Repository record for Dynamic Scene Editing via Semantically Trained 3D Guassians (opens in a new tab)

  17. Gaussian Splatting Device-Architecture Co-Design for Accelerated Physical AI Inference and Reasoning

    … robotics, autonomous driving, and XR/AR, demand 3D scene representations that are simultaneously photorealistic, memory-efficient, and computationally lean. Gaussian Splatting has established itself as the state-of-the-art technique for 3D scene representation, delivering photorealistic rendering …

    uic

  18. Infrastructure for modeling and inference engineering with 3D generative scene graphs

    … using a rich abstract representation of 3D scene geometry called a scene graph. However, there remain several challenges in the practical implementation of scene graph models, including human-editable specification, visualization, priors, structure inference, hyperparameters tuning, and …

    mit Repository record for Infrastructure for modeling and inference engineering with 3D generative scene graphs (opens in a new tab)

  19. Recognition, Mining, Synthesis and Estimation (Rmse) for Large-Scale Visual Data Using Multilinear Models

    … video mining, image-based rendering, and 3D scene modeling. In object recognition, we present a general framework for dimensionality reduction using Datum-as-Is representation. Our approach works directly on the multi-dimensional form of the data (matrix in 2D and tensor in higher …

    uiuc Repository record for Recognition, Mining, Synthesis and Estimation (Rmse) for Large-Scale Visual Data Using Multilinear Models (opens in a new tab)

  20. Image registration and its application to computer vision : mosaicing and independant motion detection

    … a single composition that represents part of a 3D scene. This is useful for many different applications, including virtual reality environments and movie special effects.

    cape-town Repository record for Image registration and its application to computer vision : mosaicing and independant motion detection (opens in a new tab)

Page 1 of 4